{"total":121,"rows":[{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2110.11624","title":"SciCap: Generating Captions for Scientific Figures","created":"2021-10-22","cited_by_count":77,"area":null},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2308.03349","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","created":"2023-08-07","cited_by_count":68,"area":null},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2210.06628","title":"OpenCQA: Open-ended Question Answering with Charts","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2304.06447","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2205.03966","title":"Chart Question Answering: State of the Art and Future Directions","created":"2022-05-08","cited_by_count":26,"area":null},{"id":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2304.02173","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","created":"2023-04-05","cited_by_count":24,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2207.07243","title":"LineCap: Line Charts for Data Visualization Captioning Models","created":"2022-07-15","cited_by_count":17,"area":null},{"id":"2407.11229","title":"Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness","created":"2024-07-15","cited_by_count":17,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2305.18641","title":"Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"area":null},{"id":"2302.12324","title":"Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization","created":"2023-02-23","cited_by_count":14,"area":null},{"id":"2309.08379","title":"PatFig: Generating Short and Long Captions for Patent Figures","created":"2023-09-15","cited_by_count":12,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2111.14792","title":"Classification-Regression for Chart Comprehension","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2503.18435","title":"On the Perception Bottleneck of VLMs for Chart Understanding","created":"2025-03-24","cited_by_count":10,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2506.02011","title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","cited_by_count":9,"area":null},{"id":"2105.14875","title":"Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2308.01979","title":"RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2506.04585","title":"MuSciClaims: Multimodal Scientific Claim Verification","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2502.15803","title":"Megrez-Omni Technical Report","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2509.22437","title":"Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2112.00800","title":"Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2305.04151","title":"Context-Aware Chart Element Detection","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2409.19747","title":"Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2501.02552","title":"Multi-LLM Collaborative Caption Generation in Scientific Documents","created":"2025-01-05","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2403.17784","title":"SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2412.17606","title":"SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2505.15046","title":"ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2510.20803","title":"ARGenSeg: Image Segmentation with Autoregressive Image Generation Model","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2305.15080","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2501.15022","title":"Using Large Language Models for education managements in Vietnamese with low resources","created":"2025-01-25","cited_by_count":4,"area":null},{"id":"2505.09952","title":"Task-Core Memory Management and Consolidation for Long-term Continual Learning","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2310.18983","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2503.00086","title":"Generalization of CNNs on Relational Reasoning with Bar Charts","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2507.01627","title":"Chart Question Answering from Real-World Analytical Narratives","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2303.01388","title":"Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2410.09761","title":"ChartKG: A Knowledge-Graph-Based Representation for Chart Images","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2509.13282","title":"ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2603.28902","title":"ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2605.29446","title":"CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2111.04190","title":"VizAI : Selecting Accurate Visualizations of Numerical Data","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2501.09521","title":"Augmenting a Large Language Model with a Combination of Text and Visual Data for Conversational Visualization of Global Geospatial Data","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2505.10043","title":"Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.16571","title":"Capturing Visualization Design Rationale","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.10138","title":"Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2605.26994","title":"ChartAct: A Benchmark for Dynamic Chart Understanding","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.27731","title":"Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.25911","title":"AnnoBench: A Benchmark for Visualization Annotation Generation","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.32041","title":"Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2211.14362","title":"Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2306.11699","title":"GenPlot: Increasing the Scale and Diversity of Chart Derendering Data","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2312.11146","title":"OsmLocator: locating overlapping scatter marks with a non-training generative perspective","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2406.17437","title":"Advancing Question Answering on Handwritten Documents: A State-of-the-Art Recognition-Based Model for HW-SQuAD","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2507.21741","title":"MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces","created":"2025-07-29","cited_by_count":0,"area":null}],"next_cursor":"100"}